DEEP TRANSFER LEARNING FOR RETINAL IMAGE ANALYSIS IN DIABETES PREDICTION: A SYSTEMATIC REVIEW
Main Article Content
Abstract
Diabetes is a chronic metabolic disorder that affects millions globally, leading to severe complications such as diabetic retinopathy (DR), which can result in vision impairment or blindness. This systematic study examines the function of deep transfer learning (TL) in the early detection of diabetes using retinal image analysis. It comprehensively examines many pre-trained convolutional neural networks (CNNs) and hybrid models employed in diabetic prediction, highlighting their architectures, datasets, performance metrics, and clinical applicability. Furthermore, this paper discusses the challenges of retinal image classification, including dataset imbalances, interpretability, and computational complexity. The study also identifies key future research directions to improve the robustness, generalizability, and clinical deployment of AI-driven diabetic prediction systems. The findings suggest deep TL (DTL) is a promising tool for noninvasive, automated, and scalable diabetes screening using retinal images.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.